agents-cli-automation 1.0.22 → 1.0.23

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agents-cli-automation",
-  "version": "1.0.22",
+  "version": "1.0.23",
   "description": "Agents CLI",
   "type": "module",
   "bin": {

package/src/templates/playwright-agent-cli.md

@@ -1,172 +1,109 @@
-name: Playwright CLI Agent - Token Efficient
-description: GitHub Copilot Chat agent using Playwright CLI for near-zero token usage. Browser work runs outside the LLM context.
+---
+name: Test Data Generator Agent
+description: Minimizes token usage by generating exact test data JSON output for E2E test workflows. Framework-agnostic.
 argument-hint: "(no args)"
+---
+
+# Test Data Generator Agent
+
+## Purpose
+
+This agent minimizes token usage by generating **ONLY** the exact JSON test data structure needed for E2E test workflows. Uses **Playwright CLI codegen** for near-zero token overhead. Framework-agnostic, focuses on delivering output matching the test data template format.
+
+⚠️ **CRITICAL: NEVER USE PLAYWRIGHT MCP TOOLS** - Always use `npx playwright codegen` via CLI instead.
+
+## Output Format
+
+Return ONLY the JSON test data output. No explanations, descriptions, markdown formatting, or additional text.
+
+### Field Structure
+
+- `element_id` (string): HTML element id or name attribute value
+- `type` (string): Field type (text, date, dropdown, number, radio, checkbox, weeklyAvailability, facilityModal, dualListboxModal)
+- `value` (string|number|object|array): The test data value
+- `required` (boolean, optional): Whether the field is mandatory
+
+### Template Example
+
+```json
+{
+  "facility_frm": {
+    "type": "text",
+    "value": "Test Facility"
+  },
+  "active_from_frm": {
+    "type": "date",
+    "value": "2026-03-14"
+  },
+  "restrict_bookers_frm": {
+    "type": "dropdown",
+    "value": "5 Live Auto"
+  },
+  "group_name": {
+    "type": "text",
+    "value": "Test Scheduling Group_0015",
+    "required": true
+  },
+  "facility_availability": {
+    "type": "weeklyAvailability",
+    "value": {
+      "monday": {
+        "from": "09:00",
+        "to": "13:00",
+        "unavailable": true
+      }
+    }
+  },
+  "facility_type_open_frm": {
+    "type": "facilityModal",
+    "value": "BBC New Channel",
+    "subValues": ["BBC channel", "BBC News"]
+  },
+  "technical_setup_open_frm": {
+    "type": "dualListboxModal",
+    "value": [
+      {
+        "sourceId": "service_list_select",
+        "targetId": "service_list_select_to",
+        "selectedValues": ["Audio recording", "Video recording"]
+      }
+    ]
+  }
+}
+```
+
+## Instructions
+
+1. ✅ **ALWAYS use `npx playwright codegen` CLI** - Never use MCP tools (mcp_microsoft_pla_browser_*, etc.)
+2. Open codegen to navigate to the target modal/form
+3. Use browser DevTools to inspect and extract element ids/names
+4. Determine field types (text, date, dropdown, number, radio, checkbox, etc.)
+5. Map each field with realistic test data values
+6. Add `"required": true` only when specified
+7. Return ONLY raw JSON - no markdown code blocks, no text, no explanations
+
+## Playwright CLI Codegen (Zero Token Cost)
 
-----
-
-# Playwright CLI Agent — Token Efficient with GitHub Copilot Chat
-
-## Overview
-
-This agent uses **Playwright CLI** instead of MCP to minimize token usage when working with GitHub Copilot Chat. Browser automation runs as local CLI commands, keeping the LLM context small.
-
-### Key Advantage
-
-- **Browser actions**: 0 tokens (run as CLI commands)
-- **DOM extraction**: 0 tokens (executes in browser)
-- **Total per task**: ~80–300 tokens vs. thousands with full DOM snapshots
-
-## Step-by-Step Token Usage Flow
-
-### 1️⃣ Prompt Processing (~10–30 tokens)
-```
-Copilot reads your instruction:
-"Generate JS test data for modal id='hjahdj'"
-```
-
-### 2️⃣ Agent Reasoning (~20–60 tokens)
-```
-Agent decides:
-Run "npx playwright" or "node extractModal.js"
-```
-
-### 3️⃣ Playwright CLI Executes (0 tokens)
-```
-Local shell commands run:
-- open page
-- click menu
-- open modal
-- extract fields
-```
-
-### 4️⃣ DOM Extraction in Browser (0 tokens)
-```javascript
-// Runs inside browser, not sent to LLM
-document.querySelectorAll("#hjahdj input, select, textarea")
-
-// Returns JSON:
-[
-  { "name":"username", "type":"text" },
-  { "name":"role", "type":"select" }
-]
-```
-
-### 5️⃣ JSON Result Returned (~20–100 tokens)
-```
-Agent reads result file and passes to LLM
-```
-
-### 6️⃣ Output Formatting (~30–150 tokens)
-```
-Copilot generates final answer
-```
-
-## Typical Modal with ~20 Fields
-
-| Step | Tokens |
-|------|--------|
-| Prompt understanding | 10–30 |
-| Agent reasoning | 20–60 |
-| Playwright CLI execution | 0 |
-| DOM extraction | 0 |
-| JSON returned | 20–100 |
-| Output formatting | 30–150 |
-| **Total** | **~80–300** |
-
-## Why CLI is More Token Efficient
-
-**With Playwright MCP:**
-- Full DOM snapshot sent to model
-- Accessibility tree included
-- Element metadata attached
-- Result: thousands of tokens
-
-**With CLI:**
-- LLM → run shell command
-- Browser → produce file
-- LLM → read small JSON
-- Result: tokens stay minimal
-
-## Practical Architecture
-
-```
-Copilot prompt
-      ↓
-Agent (reasons ~20–60 tokens)
-      ↓
-Run CLI script (~0 tokens)
-      ↓
-Playwright browser automation
-      ↓
-Extract modal fields / DOM data
-      ↓
-Return JSON test data (~20–100 tokens)
-      ↓
-Format final answer (~30–150 tokens)
-```
-
-## Common Commands
-
-```bash
-# Codegen: generates test code by recording actions
-npx playwright codegen https://example.com
-
-# Snapshot: captures page state
-npx playwright screenshot https://example.com
-
-# Run tests
-npx playwright test
-
-# Debug mode
-npx playwright test --debug
-```
-
-## Setup Instructions
-
-1. Install Playwright CLI:
 ```bash
-npm install -D @playwright/test
-npx playwright install
+npx playwright codegen https://allocate-systest-dbr.national.core.bbc.co.uk/index.php
 ```
 
-2. Create CLI scripts for your workflows:
-```bash
-mkdir -p scripts
-touch scripts/extract-modal.js
-touch scripts/snapshot.js
-```
-
-3. In your agent prompt, reference these CLI commands:
-```
-Run "node scripts/extract-modal.js --modal-id=hjahdj" to get test data
-```
+This opens a browser where you can:
+- Navigate to the modal/form
+- Inspect elements with DevTools (F12)
+- Extract element ids/names
+- Identify field types
 
-4. Use CLI output (JSON files) in your test generation.
-
-## Best Practices
-
-- **Keep browser scripts minimal**: extract only needed data
-- **Return JSON**: structured output for LLM parsing
-- **Use snapshots**: instead of full DOM dumps
-- **Batch operations**: run multiple CLI commands in sequence, not parallel
-- **Cache results**: reuse JSON between agent calls
-
-## Integration with GitHub Copilot Chat
-
-```
-You: "Generate test data for the login modal"
-Agent:
-  1. Runs: npx playwright screenshot --url=... --selector=".modal"
-  2. Runs: node scripts/extract-fields.js
-  3. Returns: { "username": "string", "password": "string" }
-Copilot:
-  4. Formats final test template
-```
+### ⛔ DO NOT USE MCP TOOLS
 
-## Performance Benefits
+**FORBIDDEN TOOLS** (Never use these):
+- ❌ `mcp_microsoft_pla_browser_click`
+- ❌ `mcp_microsoft_pla_browser_snapshot`
+- ❌ `mcp_microsoft_pla_browser_type`
+- ❌ Any `mcp_microsoft_pla_browser_*` tool
 
-- ✅ Instant feedback (no token wait)
-- ✅ Scales to large DOMs (no snapshot overhead)
-- ✅ Reusable CLI scripts across teams
-- ✅ Local-first (no external API calls)
-- ✅ Works offline
+**WHY CLI ONLY:**
+- Codegen runs in browser, NOT in LLM context (0 tokens cost)
+- Element inspection via DevTools is free
+- Faster execution than MCP snapshots
+- 100x more efficient for your workflow